© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 592
    Prev
    Next
    INDEX
    Explanations

    pip install Python packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unts
    0.44
    onomics
    0.42
    ాప
    0.38
     beaten
    0.38
     Group
    0.37
    علوم
    0.37
    ()>
    0.36
    uellement
    0.35
    ated
    0.35
     Version
    0.35
    POSITIVE LOGITS
    დეს
    0.40
    솥
    0.35
     Modal
    0.35
    SELECT
    0.35
    엣
    0.34
     finns
    0.34
     sobren
    0.34
     SELECT
    0.34
     gern
    0.34
     malesuada
    0.34
    Activations Density 0.003%

    No Known Activations